{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PHQ7GOGAAQRW2DV6AVSM2XPZ5R","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"0deea64e226037978aa5448913f18b5c27cb0c7787052741c990bf4d05b06af1","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-04T21:29:47Z","title_canon_sha256":"0923a0631cc89f621895637be75b2ab0b1d5a60920801a3e4091d0b295b7dec5"},"schema_version":"1.0","source":{"id":"2502.02732","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.02732","created_at":"2026-07-05T11:16:54Z"},{"alias_kind":"arxiv_version","alias_value":"2502.02732v3","created_at":"2026-07-05T11:16:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02732","created_at":"2026-07-05T11:16:54Z"},{"alias_kind":"pith_short_12","alias_value":"PHQ7GOGAAQRW","created_at":"2026-07-05T11:16:54Z"},{"alias_kind":"pith_short_16","alias_value":"PHQ7GOGAAQRW2DV6","created_at":"2026-07-05T11:16:54Z"},{"alias_kind":"pith_short_8","alias_value":"PHQ7GOGA","created_at":"2026-07-05T11:16:54Z"}],"graph_snapshots":[{"event_id":"sha256:c3cfe38e4fd47643a82f93834d18a13837c34138d76a9c79657d3757db07e0c9","target":"graph","created_at":"2026-07-05T11:16:54Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2502.02732/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Selecting a layer normalization (LN) strategy that stabilizes training and speeds convergence in Transformers remains difficult, even for today's large language models (LLM). We present a comprehensive analytical foundation for understanding how different LN strategies influence training dynamics in large-scale Transformers. Until recently, Pre-LN and Post-LN have long dominated practices despite their limitations in large-scale training. However, several open-source models have recently begun silently adopting a third strategy without much explanation. This strategy places normalization layer","authors_text":"Beomjun Kim, Byeongchan Lee, Cheonbok Park, Dongyoon Han, Jeonghoon Kim, Jinwoo Shin, Kang Min Yoo, Seongjin Shin, Taehwan Yoo, Yeontaek Oh","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-04T21:29:47Z","title":"Peri-LN: Revisiting Normalization Layer in the Transformer Architecture"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02732","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:2553839d2110007b4cd6aa0b5da05af570a5a72d4980f71bf89807fbbb9e975e","target":"record","created_at":"2026-07-05T11:16:54Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"0deea64e226037978aa5448913f18b5c27cb0c7787052741c990bf4d05b06af1","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-04T21:29:47Z","title_canon_sha256":"0923a0631cc89f621895637be75b2ab0b1d5a60920801a3e4091d0b295b7dec5"},"schema_version":"1.0","source":{"id":"2502.02732","kind":"arxiv","version":3}},"canonical_sha256":"79e1f338c004236d0ebe0564cd5df9ec7b352524b96c57019714bd887d4b302a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"79e1f338c004236d0ebe0564cd5df9ec7b352524b96c57019714bd887d4b302a","first_computed_at":"2026-07-05T11:16:54.731990Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:16:54.731990Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PvI36A/mRP4X/kGF8klSi/Xx8GoKdk89fp4aR47MobuOW0gVE0IUlujoDCZj7mY1rTzLKm8MKQrOYmKh9l9iAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:16:54.732490Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.02732","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2553839d2110007b4cd6aa0b5da05af570a5a72d4980f71bf89807fbbb9e975e","sha256:c3cfe38e4fd47643a82f93834d18a13837c34138d76a9c79657d3757db07e0c9"],"state_sha256":"1b2b68fcece22a1e1f8050588e99ade5bede4f4732f6682354be37439661be77"}